Model: GELU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1683 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.7990. Min Range: -5.7990

Max Act: 5.7677. Min Act: -0.1700

Data Index: 768419 (C4 (Web Text))

Max Activating Token Index: 626

Text #1

Max Range: 5.7990. Min Range: -5.7990

Max Act: 5.7990. Min Act: -0.1700

Data Index: 308215 (C4 (Web Text))

Max Activating Token Index: 572

Text #2

Max Range: 5.7990. Min Range: -5.7990

Max Act: 5.7677. Min Act: -0.1700

Data Index: 1464294 (Python Code)

Max Activating Token Index: 713

Text #3

Max Range: 5.7990. Min Range: -5.7990

Max Act: 5.7990. Min Act: -0.1700

Data Index: 1038049 (C4 (Web Text))

Max Activating Token Index: 729

Text #4

Max Range: 5.7990. Min Range: -5.7990

Max Act: 5.7365. Min Act: -0.1700

Data Index: 177318 (C4 (Web Text))

Max Activating Token Index: 740

Text #5

Max Range: 5.7990. Min Range: -5.7990

Max Act: 5.7052. Min Act: -0.1700

Data Index: 469112 (C4 (Web Text))

Max Activating Token Index: 616

Text #6

Max Range: 5.7990. Min Range: -5.7990

Max Act: 5.7365. Min Act: -0.1700

Data Index: 1254953 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 5.7990. Min Range: -5.7990

Max Act: 5.7990. Min Act: -0.1700

Data Index: 825330 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 5.7990. Min Range: -5.7990

Max Act: 5.6740. Min Act: -0.1700

Data Index: 1067247 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 5.7990. Min Range: -5.7990

Max Act: 5.6740. Min Act: -0.1700

Data Index: 786876 (C4 (Web Text))

Max Activating Token Index: 534

Text #10

Max Range: 5.7990. Min Range: -5.7990

Max Act: 5.6427. Min Act: -0.1700

Data Index: 268952 (C4 (Web Text))

Max Activating Token Index: 123

Text #11

Max Range: 5.7990. Min Range: -5.7990

Max Act: 5.7052. Min Act: -0.1700

Data Index: 1307307 (C4 (Web Text))

Max Activating Token Index: 611

Text #12

Max Range: 5.7990. Min Range: -5.7990

Max Act: 5.6427. Min Act: -0.1700

Data Index: 75049 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 5.7990. Min Range: -5.7990

Max Act: 5.6740. Min Act: -0.1700

Data Index: 843496 (C4 (Web Text))

Max Activating Token Index: 734

Text #14

Max Range: 5.7990. Min Range: -5.7990

Max Act: 5.6115. Min Act: -0.1700

Data Index: 73880 (C4 (Web Text))

Max Activating Token Index: 416

Text #15

Max Range: 5.7990. Min Range: -5.7990

Max Act: 5.6427. Min Act: -0.1700

Data Index: 506682 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 5.7990. Min Range: -5.7990

Max Act: 5.6115. Min Act: -0.1700

Data Index: 823876 (C4 (Web Text))

Max Activating Token Index: 768

Text #17

Max Range: 5.7990. Min Range: -5.7990

Max Act: 5.5802. Min Act: -0.1700

Data Index: 1195025 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 5.7990. Min Range: -5.7990

Max Act: 5.5490. Min Act: -0.1700

Data Index: 657278 (C4 (Web Text))

Max Activating Token Index: 218

Text #19

Max Range: 5.7990. Min Range: -5.7990

Max Act: 5.5177. Min Act: -0.1700

Data Index: 1215437 (C4 (Web Text))

Max Activating Token Index: 761